Fibrinogen and future cardiovascular disease in people with diabetes: aetiological associations and risk prediction using individual participant data from nine community-based prospective cohort studies

Abstract

Aims: We assessed the associations of fibrinogen levels with cardiovascular disease (CVD) risks in people with and without diabetes, and quantified the value of adding fibrinogen to the established predictive algorithms for CVD.

Methods: We used Cox models to analyse data from prospective cohorts totalling 33,091 adults (1006 with diabetes) who took part in British and Scottish general population-based health surveys. Discrimination was assessed through c-statistic.

Results: During a median follow-up of 116 months, 351 deaths (119 CVD) were recorded in participants with diabetes and 4157 deaths (1167 CVD) in those without. After adjustment for age and sex, fibrinogen (per standard deviation log(e)) was positively associated with a 34% (26-42%) higher risk of cardiovascular disease and 30% (26-35%) greater risk all-cause mortality. These associations were log-linear, similar in people with and without diabetes (p-value for interaction ≥0.21), robust to the adjustment of additional major CVD risk factors. Adding fibrinogen to a model containing conventional CVD risk factors resulted in only modest improvement in risk prediction.

Conclusions: The associations of fibrinogen with CVD and all-cause mortality are broadly similar in people with and without diabetes status. Improvement in predictive accuracy after adding fibrinogen to established risk factors is not clinically important.